superlocalmemory 3.6.14 → 3.6.16

package/CHANGELOG.md

@@ -5,6 +5,34 @@ All notable changes to SuperLocalMemory V3 will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [3.6.14] - 2026-06-18 — Audit-hardened: memory bounds, cross-tenant cache isolation, atomic credentials
+
+Shipped through two adversarial audit passes (Qualixar Iron Pattern Stages 8–9), validated against a green 5933-test suite under the real 3.12 runtime. Default single-machine behavior is unchanged.
+
+### Security
+
+- **Cross-tenant cache isolation.** The optimize proxy cache now derives a per-credential tenant from the raw inbound API key (before header redaction); two users sending the same prompt with different keys never share a cache entry, and requests with no credential are never cached. Previously every proxy response was keyed under a single shared `default` tenant — on a LAN-shared proxy that could serve user A's completion to user B.
+- **Hardened the isolation against internal hook errors.** A tenant-aware cache hook is never silently downgraded to the shared namespace when it raises an internal error — the safe path is a cache miss, decided by signature inspection rather than catching an ambiguous `TypeError`.
+- **Vertex cache keys isolate by project + region.**
+
+### Fixed — memory (bounded-memory lifeline)
+
+- **Bounded the optimize caches.** Per-tenant LRU caps on the semantic vector index and the boundary-MLE cache, plus a cap on the *number* of tenants held in memory (centroid + index shards). Eviction is lossless — the DB remains the source of truth and evicted tenants rebuild on next access. Prevents unbounded RAM growth on long-lived shared-proxy daemons.
+- **Restored the SAFE-CACHE adversarial defense**, which a 3-tuple unpack bug had been silently disabling on every warm-start with vectors present.
+
+### Fixed — reliability
+
+- **Atomic, 0600 credential writes** (`cloud_backup`): no world-readable window, no torn-write corruption of the credential store, and a fixed `UnboundLocalError` that broke the credential fallback entirely on keyring-less hosts (headless Linux / minimal Docker).
+- **ObserveBuffer** surfaces flush failures and reports an honest `evaluated/captured/failed` count instead of treating skipped items as successes.
+- **Cloud embedding** reuses a pooled HTTP client instead of opening a fresh TLS connection per call.
+- **`check_status`** distinguishes a corrupt `settings.json` (`installed=None`) from "not installed".
+
+### Fixed — packaging / platform
+
+- **Cross-platform plugin launcher** (POSIX + Windows) and a Windows venv bootstrap, so the plugin's MCP server resolves the correct `slm` binary on Windows (`Scripts/slm.exe`) as well as POSIX.
+- **Declared `tomli-w`** so the codex IDE integration can write its `.codex/config.toml`; previously `connect_ide('codex')` failed silently because the TOML writer was never a declared dependency.
+- Version reconciled to **3.6.14** across `package.json`, `pyproject.toml`, and `__init__.py`; a consistency test guards against future skew.
+
 ## [3.6.13] - 2026-06-14 — Hotfix: MCP server failed to start after upgrade
 
 ### Fixed

package/README.md

@@ -2,10 +2,10 @@
   <img src="https://superlocalmemory.com/assets/logo-mark.png" alt="SuperLocalMemory" width="200"/>
 </p>
 
-<h1 align="center">SuperLocalMemory V3.6.14</h1>
+<h1 align="center">SuperLocalMemory V3.6.16</h1>
 <p align="center"><strong>Cache. Compress. Remember. Three surfaces — proxy, MCP tools, or skill. Every setup covered.</strong><br/>
 <em>To the best of our knowledge, the only zero-cloud agent memory that beats Mem0's zero-LLM score on LoCoMo. Mode A: 74.8% vs Mem0 64.2% — no GPU, no API key, on CPU.</em></p>
-<p align="center"><code>v3.6.14</code> — <strong>Plugin-native. Profile-aware. Distributed-ready.</strong><br/>
+<p align="center"><code>v3.6.16</code> — <strong>Plugin-native. Profile-aware. Distributed-ready.</strong><br/>
 Proxy: <code>slm wrap claude</code> &nbsp;·&nbsp; MCP: add <code>slm_compress</code> to your config &nbsp;·&nbsp; Skill: zero-config</p>
 <p align="center"><strong>3 published research papers</strong> (arXiv preprints + Zenodo-archived) · <a href="https://arxiv.org/abs/2603.02240">arXiv:2603.02240</a> · <a href="https://arxiv.org/abs/2603.14588">arXiv:2603.14588</a> · <a href="https://arxiv.org/abs/2604.04514">arXiv:2604.04514</a></p>
 
@@ -100,6 +100,8 @@ Three mathematical contributions replace cloud LLM dependency:
 
 Auto-capture hooks (`slm hooks install`) fire only on real signals — topic pivot, web call, file edit — never on a timer. Fail-open, <10ms p99 hot path.
 
+**Multi-scope memory (v3.6.15, opt-in):** keep memories `personal` (default), `shared` with named profiles, or `global` across the machine. Off by default — recall only ever returns your own facts until you turn sharing on, per call or in config. See **[docs/shared-memory.md](docs/shared-memory.md)**.
+
 <a id="multilingual-embedding-support"></a>
 
 **Multilingual:** plug in any OpenAI-compatible embedding endpoint — Ollama, vLLM, LiteLLM, `bge-m3`, `multilingual-e5`, `Qwen3-Embedding`. The math layer is language-agnostic; 30+ languages work at full retrieval quality. No cloud dependency, no code changes.
@@ -160,7 +162,7 @@ Full docs: [docs/multi-machine.md](docs/multi-machine.md) · [docs/distributed-d
 |:-----|:--------|:-----|
 | **npm** (recommended) | `npm install -g superlocalmemory` | Node 14+, installs Python deps automatically |
 | **pip** | `pip install superlocalmemory` | Python 3.11+, direct install |
-| **Claude Code Plugin** (WP-06) | `/plugin install superlocalmemory@qualixar` | Self-bootstraps venv, isolated SLM_DATA_DIR, additive — 14-tool core |
+| **Claude Code Plugin** (WP-06) | `/plugin marketplace add qualixar/superlocalmemory` then `/plugin install superlocalmemory@qualixar` | Self-bootstraps venv, isolated SLM_DATA_DIR, additive — 14-tool core. Ships the skills/agents/hooks/commands |
 | **Portable / IDE connect** (WP-08) | `slm connect <ide> [--here]` | Wire any IDE without reinstalling; `slm connect claude-code` → plugin pointer |
 
 After any install path: `slm setup` → `slm doctor` → `slm warmup` (optional, pre-downloads ~500MB embedding model).
@@ -216,18 +218,31 @@ Per-IDE configs available for Claude Code, Cursor, Windsurf, VS Code Copilot, Co
 
 ## Claude Code Plugin
 
-Install directly in Claude Code without a system-level npm/pip install:
+Install directly in Claude Code — no system-level npm/pip needed. This is how you
+get the **skills, agents, hooks, commands, and rules** (the MCP server is
+bootstrapped automatically). It is a two-step flow — add the marketplace once,
+then install:
 
 ```bash
+# 1. Add the Qualixar marketplace (one-time — the repo IS the marketplace)
+/plugin marketplace add qualixar/superlocalmemory
+
+# 2. Install the plugin
 /plugin install superlocalmemory@qualixar
 ```
 
 - Self-bootstraps a Python venv, installs all deps in an isolated `SLM_DATA_DIR`
-- Registers 14-tool core MCP surface (`core14` profile by default)
+- Registers the 14-tool core MCP surface (`core14` profile by default)
+- Ships the SLM skills / agents / hooks / commands / rules
 - Additive — does not replace an existing SLM install
 - `slm connect claude-code` detects an existing plugin install and links them
 
-See [docs/getting-started.md](docs/getting-started.md) for full plugin walkthrough.
+> **Plugin vs `pip`/`npm`:** `pip install superlocalmemory` / `npm i -g superlocalmemory`
+> give you the `slm` CLI + the MCP server (the *tools*). The **skills/agents/hooks/
+> commands** come only through the plugin above. Use the plugin for Claude Code; use
+> pip/npm for the CLI or other IDEs.
+
+To update later: `/plugin marketplace update qualixar` then `/plugin install superlocalmemory@qualixar`.
 
 ---
 
@@ -292,6 +307,8 @@ slm dashboard    # Opens at http://localhost:8765
 
 | Version | Codename | Key Features |
 |---|---|---|
+| **v3.6.16** | Docs | Corrected Claude Code plugin install — adds the required `/plugin marketplace add` step; clarifies plugin vs pip/npm delivery |
+| **v3.6.15** | Multi-scope | **Opt-in [shared memory](docs/shared-memory.md)** (personal/shared/global, off by default), default-deny scope at every read path, recall scope-race fix, contributor PRs #42/#43/#44, fixes #46–#49 |
 | **v3.6.14** | Plugin-native | Claude Code Plugin (WP-06), MCP profiles (WP-01), IDE connect (WP-08), asset consolidation, UI polish (WP-12) |
 | **v3.6.x** | Optimize Everywhere / Distributed-ready | Three surfaces (proxy/MCP/skill), `SLM_REMOTE=1` LAN mode, remote dashboard, custom LLM endpoints |
 | **v3.5.0** | Scale-Ready | CozoDB/LanceDB, 6-channel recall <1s, Core Memory Block, context injection v2, score normalization |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory",
-  "version": "3.6.14",
+  "version": "3.6.16",
   "description": "Information-geometric agent memory with mathematical guarantees. 4-channel retrieval, Fisher-Rao similarity, zero-LLM mode, EU AI Act compliant. Works with Claude, Cursor, Windsurf, and 17+ AI tools.",
   "keywords": [
     "ai-memory",

package/plugin/.claude-plugin/plugin.json

@@ -16,5 +16,5 @@
   "mcpServers": "./.mcp.json",
   "name": "superlocalmemory",
   "repository": "https://github.com/qualixar/superlocalmemory",
-  "version": "3.6.14"
+  "version": "3.6.16"
 }

package/plugin/CLAUDE.md

@@ -1,4 +1,4 @@
-<!-- BEGIN SuperLocalMemory v3.6.14 -->
+<!-- BEGIN SuperLocalMemory v3.6.16 -->
 
 ## SuperLocalMemory (SLM) — Agent Rules
 
@@ -12,6 +12,7 @@ Call `session_init(project_path, query)` ONCE per fresh session before any recal
 - Recall-before-remember: `recall(query, 5)` first; use `update_memory` if near-match found.
 - Always supply tags + project + importance (7–10 for blockers/security/architecture).
 - Never dump a whole file; never claim "saved" without success:true.
+- Scope is opt-in (v3.6.15): writes are `personal`/private by default. Only use `scope="shared"/"global"` (or recall's `include_global`/`include_shared`) when the user explicitly asks to share across local profiles.
 
 ### Recall
 - `recall` for conceptual/semantic queries; `search` for exact keywords.
@@ -27,7 +28,7 @@ Call `session_init(project_path, query)` ONCE per fresh session before any recal
 `close_session(session_id)` when work is meaningfully complete.
 
 ### CLI fallback (MCP down)
-`slm recall "<q>" --limit N` · `slm search "<q>"` · `slm remember "<c>" --tags t --importance N` · `slm list --limit N` · `slm forget` (preview first) · `slm status` · `slm optimize status`
+`slm recall "<q>" --limit N` · `slm search "<q>"` · `slm remember "<c>" --tags t` · `slm list --limit N` · `slm forget` (preview first) · `slm status` · `slm optimize status`
 
 ### Skills
 slm-recall · slm-remember · slm-session · slm-status · slm-cache · slm-compress · slm-graph
@@ -38,6 +39,6 @@ slm-recall · slm-remember · slm-session · slm-status · slm-cache · slm-comp
 ### Subagents
 slm-memory-advisor (memory decisions, session hygiene) · slm-optimize-advisor (context compression + KV cache)
 
-<!-- END SuperLocalMemory v3.6.14 -->
+<!-- END SuperLocalMemory v3.6.16 -->
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin/agents/slm-memory-advisor.md

@@ -17,9 +17,9 @@ When the main agent: starts a session and hasn't loaded project context; is abou
 
 # Tools you may use (real SLM MCP tools, core profile)
 - `session_init(project_path, query, max_results, max_age_days)` — ONCE at session start; returns recent decisions + relevant memories.
-- `recall(query, limit, session_id, fast)` — multi-channel semantic retrieval (default limit 10).
+- `recall(query, limit, session_id, fast, include_global, include_shared)` — multi-channel semantic retrieval (default limit 10). Leave `include_global`/`include_shared` unset — recall is private-by-default (v3.6.15).
 - `search(query, limit, profile_id)` — exact keyword / FTS5 BM25.
-- `remember(content, tags, project, importance, session_id)` — store atomic fact; importance 1-10.
+- `remember(content, tags, project, importance, session_id, scope, shared_with)` — store atomic fact; importance 1-10. Leave `scope` unset (defaults to `personal`/private).
 - `update_memory(fact_id, content)` — correct by exact id.
 - `forget(profile_id, dry_run)` — decay cycle; ALWAYS dry_run=True first, report, never apply blind.
 - `list_recent(limit)` — newest first.
@@ -33,11 +33,12 @@ When the main agent: starts a session and hasn't loaded project context; is abou
 5. recall vs search — recall for conceptual; search for literal keyword.
 6. EMPTY/LOW results → broaden, try search, or list_recent; never fabricate.
 7. SESSION END — close_session(session_id) when work meaningfully complete.
+8. SCOPE IS OPT-IN (v3.6.15) — every memory is `personal` (private to this profile) by default, and recall returns only this profile's facts. Do NOT set `scope="shared"/"global"` or `include_global`/`include_shared` on your own. Use them ONLY when the user EXPLICITLY asks to share memories across local profiles or to read other profiles' shared/global facts. Default behaviour is identical to single-profile SLM.
 
 # CLI fallback (MCP unavailable)
-recall→`slm recall "<q>" --limit N` · search→`slm search "<q>"` · remember→`slm remember "<c>" --tags a,b --project p --importance N` · list→`slm list --limit N` · forget→`slm forget` (preview first) · status→`slm status`. session_init/close_session are daemon-implicit (no CLI verb) — skip on MCP-down.
+recall→`slm recall "<q>" --limit N` (add `--include-global`/`--include-shared` only on explicit user request) · search→`slm search "<q>"` · remember→`slm remember "<c>" --tags a,b` (project/importance are MCP-only, NOT CLI flags; `--scope shared --shared-with a,b` only when the user asks to share) · list→`slm list --limit N` · forget→`slm forget` (preview first) · status→`slm status`. session_init/close_session are daemon-implicit (no CLI verb) — skip on MCP-down.
 
 # What NOT to do
 Never session_init twice; never forget dry_run=False without reporting preview; never dump a whole file into remember; never invent a memory; never claim "saved" without success:true / clean CLI exit.
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin/agents/slm-optimize-advisor.md

@@ -35,4 +35,4 @@ stats→`slm optimize status`/`savings` · compress→`slm compress` · cache→
 # What NOT to do
 Never compress code-for-edit/JSON-to-parse/<500 chars; never store secrets/ccr_ids; never let optimize failure block/alter the task; never claim a specific savings %.
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin/requirements.txt

@@ -1 +1 @@
-superlocalmemory==3.6.14
+superlocalmemory==3.6.16

package/plugin/skills/slm-cache/SKILL.md

@@ -137,4 +137,4 @@ These subcommands control daemon-level cache settings. They do not read or write
 
 ---
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin/skills/slm-compress/SKILL.md

@@ -140,4 +140,4 @@ Content over 1 MB (1 000 000 bytes UTF-8) is processed but `reversible` is force
 
 ---
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin/skills/slm-graph/SKILL.md

@@ -297,4 +297,4 @@ Without this, the six graph tools are not registered and will appear as unknown
 
 ---
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin/skills/slm-recall/SKILL.md

@@ -164,6 +164,9 @@ No benchmark numbers are cited here; performance is workload-dependent.
 # Multi-channel semantic recall
 slm recall "<query>" [--limit N] [--fast] [--json]
 
+# Opt into shared/global facts for one query (v3.6.15 — off by default)
+slm recall "<query>" --include-global --include-shared
+
 # Keyword/FTS5 search (alias: slm search)
 slm search "<query>" [--limit N] [--json]
 
@@ -175,11 +178,16 @@ slm list [--limit N] [--json]
 ```
 
 Flags verified in source (main.py):
-- `slm recall`: `--limit`, `--fast`, `--json`
+- `slm recall`: `--limit`, `--fast`, `--json`, `--include-global` / `--no-global`, `--include-shared` / `--no-shared`
 - `slm search`: `--limit`, `--json`
 - `slm trace`: `--limit`, `--json`
 - `slm list`: `--limit` / `-n`, `--json`
 
+> **Multi-scope (v3.6.15, opt-in):** recall is shared-OFF by default — it returns only
+> this profile's facts. Pass `--include-global` / `--include-shared` (or the MCP
+> `include_global` / `include_shared` args) to opt in for a query, or set the defaults in
+> your `mode_a/b/c.json` config. See [docs/shared-memory.md](../../../docs/shared-memory.md).
+
 **Flags that do NOT exist** (fabricated in old skills — never write these):
 `--min-score`, `--format`, `--project`, `--tags` on recall or search.
 
@@ -193,4 +201,4 @@ trusts that what you surface came from the store.
 
 ---
 
-*SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later*

package/plugin/skills/slm-remember/SKILL.md

@@ -103,9 +103,16 @@ remember(
   project: str = "",  # project scope, e.g. "superlocalmemory"
   importance: int = 5,# 1–10; see scale below
   session_id: str = "",# from session_init; attributes the write to this session
+  scope: str = None,   # v3.6.15 multi-scope: "personal" (default) | "shared" | "global"
+  shared_with: str = "",# comma-separated profile_ids for scope="shared"
 )
 ```
 
+> **Multi-scope (v3.6.15, opt-in):** leave `scope` unset for `personal` (private to
+> this profile — the default, identical to 3.6.14). `"global"` is visible to every
+> profile on the machine; `"shared"` is visible to the profiles in `shared_with`.
+> See [docs/shared-memory.md](../../../docs/shared-memory.md).
+
 **importance scale:**
 - 1–3: Low — passing notes, ideas, soft preferences
 - 4–6: Normal — patterns, conventions, standard decisions (default: 5)
@@ -159,8 +166,13 @@ Always run `--dry-run` first and review the preview before passing `--yes`.
 # Store a fact
 slm remember "<content>" [--tags a,b,c] [--json]
 
-# Flags verified in source (main.py): --tags, --json, --sync
+# Store a shared/global fact (v3.6.15, opt-in)
+slm remember "<content>" --scope global
+slm remember "<content>" --scope shared --shared-with alice,bob
+
+# Flags verified in source (main.py): --tags, --json, --sync, --scope, --shared-with
 # --sync: wait for full enrichment before returning (default is async)
+# --scope: personal (default) | shared | global ; --shared-with: profile ids for shared
 ```
 
 **Flags that do NOT exist** on `slm remember`:
@@ -179,4 +191,4 @@ slm remember "<content>" [--tags a,b,c] [--json]
 
 ---
 
-*SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later*

package/plugin/skills/slm-session/SKILL.md

@@ -204,4 +204,4 @@ slm doctor [--json]    # preflight check including daemon and embedding worker
 
 ---
 
-*SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later*

package/plugin/skills/slm-status/SKILL.md

@@ -146,4 +146,4 @@ Note: the `slm optimize` subcommands have known pre-existing parse-test failures
 
 ---
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin-src/agents/slm-memory-advisor.md

@@ -17,9 +17,9 @@ When the main agent: starts a session and hasn't loaded project context; is abou
 
 # Tools you may use (real SLM MCP tools, core profile)
 - `session_init(project_path, query, max_results, max_age_days)` — ONCE at session start; returns recent decisions + relevant memories.
-- `recall(query, limit, session_id, fast)` — multi-channel semantic retrieval (default limit 10).
+- `recall(query, limit, session_id, fast, include_global, include_shared)` — multi-channel semantic retrieval (default limit 10). Leave `include_global`/`include_shared` unset — recall is private-by-default (v3.6.15).
 - `search(query, limit, profile_id)` — exact keyword / FTS5 BM25.
-- `remember(content, tags, project, importance, session_id)` — store atomic fact; importance 1-10.
+- `remember(content, tags, project, importance, session_id, scope, shared_with)` — store atomic fact; importance 1-10. Leave `scope` unset (defaults to `personal`/private).
 - `update_memory(fact_id, content)` — correct by exact id.
 - `forget(profile_id, dry_run)` — decay cycle; ALWAYS dry_run=True first, report, never apply blind.
 - `list_recent(limit)` — newest first.
@@ -33,11 +33,12 @@ When the main agent: starts a session and hasn't loaded project context; is abou
 5. recall vs search — recall for conceptual; search for literal keyword.
 6. EMPTY/LOW results → broaden, try search, or list_recent; never fabricate.
 7. SESSION END — close_session(session_id) when work meaningfully complete.
+8. SCOPE IS OPT-IN (v3.6.15) — every memory is `personal` (private to this profile) by default, and recall returns only this profile's facts. Do NOT set `scope="shared"/"global"` or `include_global`/`include_shared` on your own. Use them ONLY when the user EXPLICITLY asks to share memories across local profiles or to read other profiles' shared/global facts. Default behaviour is identical to single-profile SLM.
 
 # CLI fallback (MCP unavailable)
-recall→`slm recall "<q>" --limit N` · search→`slm search "<q>"` · remember→`slm remember "<c>" --tags a,b --project p --importance N` · list→`slm list --limit N` · forget→`slm forget` (preview first) · status→`slm status`. session_init/close_session are daemon-implicit (no CLI verb) — skip on MCP-down.
+recall→`slm recall "<q>" --limit N` (add `--include-global`/`--include-shared` only on explicit user request) · search→`slm search "<q>"` · remember→`slm remember "<c>" --tags a,b` (project/importance are MCP-only, NOT CLI flags; `--scope shared --shared-with a,b` only when the user asks to share) · list→`slm list --limit N` · forget→`slm forget` (preview first) · status→`slm status`. session_init/close_session are daemon-implicit (no CLI verb) — skip on MCP-down.
 
 # What NOT to do
 Never session_init twice; never forget dry_run=False without reporting preview; never dump a whole file into remember; never invent a memory; never claim "saved" without success:true / clean CLI exit.
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin-src/agents/slm-optimize-advisor.md

@@ -35,4 +35,4 @@ stats→`slm optimize status`/`savings` · compress→`slm compress` · cache→
 # What NOT to do
 Never compress code-for-edit/JSON-to-parse/<500 chars; never store secrets/ccr_ids; never let optimize failure block/alter the task; never claim a specific savings %.
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin-src/commands/slm-optimize.md

@@ -19,4 +19,4 @@ Rules (apply strictly):
 
 MCP unavailable → CLI fallback: `slm optimize status`.
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin-src/commands/slm-recall.md

@@ -13,4 +13,4 @@ Recall from SuperLocalMemory using the query: $ARGUMENTS
    - `slm recall "$ARGUMENTS" --limit 10`
    - then `slm search "$ARGUMENTS"`
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin-src/commands/slm-remember.md

@@ -11,6 +11,6 @@ Save to SuperLocalMemory: $ARGUMENTS
 3. Determine importance: use 8 for blockers/security/architecture decisions; use 7 for conventions and constraints; use 5 for general facts.
 4. Call `remember(content="$ARGUMENTS", tags=<extracted tags>, importance=<n>)`.
 5. Confirm only on success:true. If success is not true, report the error — never claim "saved."
-6. MCP unavailable → CLI fallback: `slm remember "$ARGUMENTS" --tags <tags> --importance <n>`.
+6. MCP unavailable → CLI fallback: `slm remember "$ARGUMENTS" --tags <tags>` (note: `--importance` is MCP-only, not a CLI flag).
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin-src/commands/slm-status.md

@@ -12,4 +12,4 @@ Show SuperLocalMemory status and optimization counters.
 
 Note: MCP get_status is intentionally NOT used here — it is outside the core profile and would error. Use `slm status` (CLI) + `slm_optimize_stats` (MCP) only.
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin-src/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "3.6.14",
+  "version": "3.6.16",
   "pluginName": "superlocalmemory",
   "displayName": "SuperLocalMemory",
   "repository": "https://github.com/qualixar/superlocalmemory",

package/plugin-src/requirements.txt

@@ -1 +1 @@
-superlocalmemory==3.6.14
+superlocalmemory==3.6.16

package/plugin-src/rules/AGENTS.md

@@ -18,6 +18,7 @@ Call `session_init(project_path, query, max_results, max_age_days)` **once** at
 - **Recall before remember** — call `recall(query, 5)` first. If a near-identical memory exists, use `update_memory(fact_id, content)` to correct it; never duplicate.
 - **Tags + project + importance** — always supply meaningful tags and the project name. Use importance 7–10 for blockers, security findings, and architecture decisions; 5 for general facts.
 - **Never dump a whole file** — extract only the durable decision or constraint; store the path reference if needed.
+- **Scope is opt-in (v3.6.15)** — memories are `personal` (private to this profile) by default. Only pass `scope="shared"/"global"` (or recall's `include_global`/`include_shared`) when the user EXPLICITLY asks to share across local profiles. Never opt in on your own; the default is identical to single-profile SLM.
 
 ---
 
@@ -56,7 +57,7 @@ When the SLM MCP server is unavailable, use these CLI equivalents:
 |------------------------|-----------------------------------------------------------|
 | `recall`               | `slm recall "<query>" --limit N`                          |
 | `search`               | `slm search "<query>"`                                    |
-| `remember`             | `slm remember "<content>" --tags a,b --project p --importance N` |
+| `remember`             | `slm remember "<content>" --tags a,b` (project/importance are MCP-only) |
 | `list_recent`          | `slm list --limit N`                                      |
 | `forget`               | `slm forget` (always preview first)                       |
 | `slm_optimize_stats`   | `slm optimize status` / `slm optimize savings`            |
@@ -72,8 +73,8 @@ When the SLM MCP server is unavailable, use these CLI equivalents:
 
 | Tool               | Signature (key params)                                                         | Notes                              |
 |--------------------|--------------------------------------------------------------------------------|------------------------------------|
-| `remember`         | `content, tags="", project="", importance=5, session_id="", agent_id`         | Store atomic fact                  |
-| `recall`           | `query, limit=10, agent_id, session_id="", fast=False`                         | Multi-channel semantic retrieval   |
+| `remember`         | `content, tags="", project="", importance=5, session_id="", scope="personal", shared_with=""` | Store atomic fact. `scope` opt-in (personal default) |
+| `recall`           | `query, limit=10, agent_id, session_id="", fast=False, include_global, include_shared`         | Multi-channel retrieval. Scope flags off by default |
 | `search`           | `query, limit=10, profile_id=""`                                               | FTS5 BM25 keyword search           |
 | `fetch`            | `url, ...`                                                                     | Fetch remote content               |
 | `list_recent`      | `limit=20, profile_id=""`                                                      | Newest memories first              |
@@ -87,4 +88,4 @@ When the SLM MCP server is unavailable, use these CLI equivalents:
 | `slm_cache_get`    | `key`                                                                          | KV cache get; returns hit, value   |
 | `slm_optimize_stats` | `()`                                                                         | Returns compress_runs, tokens_saved_compress, cache_kv_hits |
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin-src/rules/CLAUDE.md.fragment

@@ -1,4 +1,4 @@
-<!-- BEGIN SuperLocalMemory v3.6.14 -->
+<!-- BEGIN SuperLocalMemory v3.6.16 -->
 
 ## SuperLocalMemory (SLM) — Agent Rules
 
@@ -12,6 +12,7 @@ Call `session_init(project_path, query)` ONCE per fresh session before any recal
 - Recall-before-remember: `recall(query, 5)` first; use `update_memory` if near-match found.
 - Always supply tags + project + importance (7–10 for blockers/security/architecture).
 - Never dump a whole file; never claim "saved" without success:true.
+- Scope is opt-in (v3.6.15): writes are `personal`/private by default. Only use `scope="shared"/"global"` (or recall's `include_global`/`include_shared`) when the user explicitly asks to share across local profiles.
 
 ### Recall
 - `recall` for conceptual/semantic queries; `search` for exact keywords.
@@ -27,7 +28,7 @@ Call `session_init(project_path, query)` ONCE per fresh session before any recal
 `close_session(session_id)` when work is meaningfully complete.
 
 ### CLI fallback (MCP down)
-`slm recall "<q>" --limit N` · `slm search "<q>"` · `slm remember "<c>" --tags t --importance N` · `slm list --limit N` · `slm forget` (preview first) · `slm status` · `slm optimize status`
+`slm recall "<q>" --limit N` · `slm search "<q>"` · `slm remember "<c>" --tags t` · `slm list --limit N` · `slm forget` (preview first) · `slm status` · `slm optimize status`
 
 ### Skills
 slm-recall · slm-remember · slm-session · slm-status · slm-cache · slm-compress · slm-graph
@@ -38,6 +39,6 @@ slm-recall · slm-remember · slm-session · slm-status · slm-cache · slm-comp
 ### Subagents
 slm-memory-advisor (memory decisions, session hygiene) · slm-optimize-advisor (context compression + KV cache)
 
-<!-- END SuperLocalMemory v3.6.14 -->
+<!-- END SuperLocalMemory v3.6.16 -->
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin-src/skills/slm-cache/SKILL.md

@@ -137,4 +137,4 @@ These subcommands control daemon-level cache settings. They do not read or write
 
 ---
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin-src/skills/slm-compress/SKILL.md

@@ -140,4 +140,4 @@ Content over 1 MB (1 000 000 bytes UTF-8) is processed but `reversible` is force
 
 ---
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin-src/skills/slm-graph/SKILL.md

@@ -297,4 +297,4 @@ Without this, the six graph tools are not registered and will appear as unknown
 
 ---
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/plugin-src/skills/slm-recall/SKILL.md

@@ -164,6 +164,9 @@ No benchmark numbers are cited here; performance is workload-dependent.
 # Multi-channel semantic recall
 slm recall "<query>" [--limit N] [--fast] [--json]
 
+# Opt into shared/global facts for one query (v3.6.15 — off by default)
+slm recall "<query>" --include-global --include-shared
+
 # Keyword/FTS5 search (alias: slm search)
 slm search "<query>" [--limit N] [--json]
 
@@ -175,11 +178,16 @@ slm list [--limit N] [--json]
 ```
 
 Flags verified in source (main.py):
-- `slm recall`: `--limit`, `--fast`, `--json`
+- `slm recall`: `--limit`, `--fast`, `--json`, `--include-global` / `--no-global`, `--include-shared` / `--no-shared`
 - `slm search`: `--limit`, `--json`
 - `slm trace`: `--limit`, `--json`
 - `slm list`: `--limit` / `-n`, `--json`
 
+> **Multi-scope (v3.6.15, opt-in):** recall is shared-OFF by default — it returns only
+> this profile's facts. Pass `--include-global` / `--include-shared` (or the MCP
+> `include_global` / `include_shared` args) to opt in for a query, or set the defaults in
+> your `mode_a/b/c.json` config. See [docs/shared-memory.md](../../../docs/shared-memory.md).
+
 **Flags that do NOT exist** (fabricated in old skills — never write these):
 `--min-score`, `--format`, `--project`, `--tags` on recall or search.
 
@@ -193,4 +201,4 @@ trusts that what you surface came from the store.
 
 ---
 
-*SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later*

package/plugin-src/skills/slm-remember/SKILL.md

@@ -103,9 +103,16 @@ remember(
   project: str = "",  # project scope, e.g. "superlocalmemory"
   importance: int = 5,# 1–10; see scale below
   session_id: str = "",# from session_init; attributes the write to this session
+  scope: str = None,   # v3.6.15 multi-scope: "personal" (default) | "shared" | "global"
+  shared_with: str = "",# comma-separated profile_ids for scope="shared"
 )
 ```
 
+> **Multi-scope (v3.6.15, opt-in):** leave `scope` unset for `personal` (private to
+> this profile — the default, identical to 3.6.14). `"global"` is visible to every
+> profile on the machine; `"shared"` is visible to the profiles in `shared_with`.
+> See [docs/shared-memory.md](../../../docs/shared-memory.md).
+
 **importance scale:**
 - 1–3: Low — passing notes, ideas, soft preferences
 - 4–6: Normal — patterns, conventions, standard decisions (default: 5)
@@ -159,8 +166,13 @@ Always run `--dry-run` first and review the preview before passing `--yes`.
 # Store a fact
 slm remember "<content>" [--tags a,b,c] [--json]
 
-# Flags verified in source (main.py): --tags, --json, --sync
+# Store a shared/global fact (v3.6.15, opt-in)
+slm remember "<content>" --scope global
+slm remember "<content>" --scope shared --shared-with alice,bob
+
+# Flags verified in source (main.py): --tags, --json, --sync, --scope, --shared-with
 # --sync: wait for full enrichment before returning (default is async)
+# --scope: personal (default) | shared | global ; --shared-with: profile ids for shared
 ```
 
 **Flags that do NOT exist** on `slm remember`:
@@ -179,4 +191,4 @@ slm remember "<content>" [--tags a,b,c] [--json]
 
 ---
 
-*SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later*

package/plugin-src/skills/slm-session/SKILL.md

@@ -204,4 +204,4 @@ slm doctor [--json]    # preflight check including daemon and embedding worker
 
 ---
 
-*SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later*

package/plugin-src/skills/slm-status/SKILL.md

@@ -146,4 +146,4 @@ Note: the `slm optimize` subcommands have known pre-existing parse-test failures
 
 ---
 
-SuperLocalMemory v3.6.14 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.16 · Qualixar · AGPL-3.0-or-later

package/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "superlocalmemory"
-version = "3.6.14"
+version = "3.6.16"
 description = "Information-geometric agent memory with mathematical guarantees"
 readme = "README.md"
 license = {text = "AGPL-3.0-or-later"}

package/scripts/build-plugin.js

@@ -30,7 +30,7 @@ import process from 'node:process';
 // ---------------------------------------------------------------------------
 // Constants
 // ---------------------------------------------------------------------------
-const VERSION = '3.6.14';
+const VERSION = '3.6.16';
 const MANIFEST_REL = 'plugin-src/manifest.json';
 const GENERATED_BANNER = `# _GENERATED — DO NOT HAND-EDIT
 

package/src/superlocalmemory/__init__.py

@@ -32,7 +32,7 @@ if "OMP_NUM_THREADS" not in os.environ:
     os.environ["OMP_NUM_THREADS"] = "2"
 # ---------------------------------------------------------------------------
 
-__version__ = "3.6.14"
+__version__ = "3.6.16"
 
 _REQUIRED_VERSIONS = {
     "sentence_transformers": "5.3.0",